# On the Role of Time in Learning

## TL;DR

This paper argues that traditional temporal learning models like RNNs may overlook the fundamental nature of time, proposing a physics-inspired approach based on the principle of Least Cognitive Action that models learning through differential equations.

## Contribution

It introduces a novel learning framework grounded in the principle of Least Cognitive Action, offering a deeper interpretation of time in learning processes compared to traditional methods.

## Key findings

- Reformulation of learning using Least Cognitive Action principle.
- Learning process described by differential equations.
- Potential for a more natural integration of physical laws into learning models.

## Abstract

By and large the process of learning concepts that are embedded in time is regarded as quite a mature research topic. Hidden Markov models, recurrent neural networks are, amongst others, successful approaches to learning from temporal data. In this paper, we claim that the dominant approach minimizing appropriate risk functions defined over time by classic stochastic gradient might miss the deep interpretation of time given in other fields like physics. We show that a recent reformulation of learning according to the principle of Least Cognitive Action is better suited whenever time is involved in learning. The principle gives rise to a learning process that is driven by differential equations, that can somehow descrive the process within the same framework as other laws of nature.